fix traditional

app.py

@@ -6,16 +6,19 @@
 
 
 import traceback
-import time
 import copy
+import time
 import sys
-import re
 import os
+import re
 os.environ["MACRO_CORRECT_FLAG_CSC_TOKEN"] = "1"
 os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
 os.environ["USE_TORCH"] = "1"
 
 from macro_correct.pytorch_textcorrection.tcTools import preprocess_same_with_training
+from macro_correct.pytorch_textcorrection.tcTools import get_errors_for_difflib
+from macro_correct.pytorch_textcorrection.tcTools import cut_sent_by_maxlen
+from macro_correct.pytorch_textcorrection.tcTools import count_flag_zh
 from macro_correct import correct_basic
 from macro_correct import correct_long
 from macro_correct import correct
@@ -79,14 +82,27 @@ def cut_sent_by_stay_and_maxlen(text, max_len=126, return_length=True):
 
 def macro_correct(text):
     print(text)
-    text = preprocess_same_with_training(text)
     texts, texts_length = cut_sent_by_stay_and_maxlen(text, return_length=True)
     text_str = ""
     text_list = []
     for t in texts:
         print(t)
-        text_csc = correct_long(t, num_rethink=2, flag_cut=True)
+        t_process = preprocess_same_with_training(t)
+        text_csc = correct_long(t_process, num_rethink=2, flag_cut=True, limit_length_char=1)
         print(text_csc)
+        ### 繁简
+        if t != t_process:
+            t_correct, errors = get_errors_for_difflib(t_process, t)
+            errors_new = []
+            for err in errors:
+                if count_flag_zh(err[0]) and count_flag_zh(err[1]):
+                    errors_new.append(err + [1])
+            if errors_new:
+                if text_csc:
+                    text_csc[0]["errors"] += errors_new
+                else:
+                    text_csc = [{"source": t, "target": t_process, "errors": errors_new}]
+        ### 本身的错误
         if text_csc:
             text_list.extend(text_csc)
             text_str += text_csc[0].get("target")
@@ -120,16 +136,9 @@ if __name__ == '__main__':
         macro_correct,
         inputs='text',
         outputs='text',
-        title="Chinese Spelling Correction Model Macropodus/macbert4mdcspell_v2",
+        title="Chinese Spelling Correction Model Macropodus/macbert4csc_v2",
         description="Copy or input error Chinese text. Submit and the machine will correct text.",
         article="Link to <a href='https://github.com/yongzhuo/macro-correct' style='color:blue;' target='_blank\'>Github REPO: macro-correct</a>",
         examples=examples
     ).launch()
     # ).launch(server_name="0.0.0.0", server_port=8066, share=False, debug=True)
-
-"""
-赤热的阳光烘烤大地，婵鸣撕破树荫的宁净。少年咬下鲜红西瓜，糖汁溶化在沙摊上。孩童举着冰其淋奔跑，浪花打湿嘻闹的脚丫。威风卷起碎花裙摆，牵牛花在篱笆绽方。这个季结，连空气都浸着清谅的甜。
-炽热的阳光烘烤大地,蝉鸣撕破树荫的宁静。少年咬下鲜红西瓜,糖汁溶化在沙滩上。孩童举着冰淇淋奔跑,浪花打湿嬉闹的脚丫。微风卷起碎花裙摆,牵牛花在篱笆绽放。这个季节,连空气都浸着清凉的甜。
-
-pyinstaller --onefile app_macro_correct_std.py
-"""